© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 61219
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cantor
    -1.03
    メリカ
    -1.02
     argento
    -1.02
     precin
    -1.01
     inaug
    -0.98
    瞜
    -0.98
     toller
    -0.98
     pylint
    -0.97
     spela
    -0.97
    古屋
    -0.96
    POSITIVE LOGITS
     to
    1.22
     with
    1.05
     upon
    0.95
    actéristique
    0.89
    vdots
    0.87
     Reference
    0.87
    jerk
    0.87
     με
    0.85
     requieren
    0.85
     butterknife
    0.84
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.